Patent Value Calculation

Abstract

Techniques for calculating patent value and predicting patent potential are described herein. These techniques may include calculating the value of a patent based on associations between a patent and other patents. The value of the patent may be calculated based on a citation in another patent to the patent, and a citation in the patent to a further patent. These techniques may also include predicting a potential value of a patent on the basis of a plurality of patent values and displaying this potential to a user.

1 . A method of calculating a value of a patent, comprising:
 identifying a forward citation and a backward citation of a first patent, the forward citation being a citation in a second patent to the first patent, the backward citation being a citation in the first patent to a third patent;   weighting at least one of the forward and backward citations; and   calculating a value of the first patent based at least in part on at least the weighted forward citation or the weighted backward citation.   
     
     
         2 . The method of  claim 1 , wherein:
 the identifying comprises identifying each forward citation and each backward citation of the first patent;   the weighting comprises weighting each of the forward citations and each of the backward citations; and   the calculating comprises calculating the value of the first patent based at least in part on each of the weighted forward citations and each of the weighted backward citations.   
     
     
         3 . The method of  claim 1 , wherein the calculating includes:
 representing the forward and backward citations in a matrix;   sorting the matrix;   augmenting the sorted matrix by adding a row and a column to the matrix;   normalizing rows within the augmented matrix; and   solving the normalized matrix.   
     
     
         4 . The method of  claim 3 , wherein the sorting includes classifying the first patent and corresponding citations, and reorganizing the matrix based at least in part on the classification. 
     
     
         5 . The method of  claim 3 , wherein the augmenting includes weighting an element within the added column or added row. 
     
     
         6 . The method of  claim 3 , wherein the normalizing includes utilizing matrix algebra. 
     
     
         7 . The method of  claim 3 , wherein the solving includes solving for t from the normalized matrix such that normalized t has a minimum score of one, t being a vector which is solved from the matrix. 
     
     
         8 . The method of  claim 3 , wherein the solving includes utilizing at least one of a power method and a linear-algebra method. 
     
     
         9 . The method of  claim 1 , wherein the weighting includes weighting the forward citation based at least in part on a value of the second patent, and weighting the backward citation based at least in part on a value of the third patent. 
     
     
         10 . The method of  claim 9 , wherein the value of the second patent is based at least in part on forward and/or backward citations of the second patent, and the value of the third patent is based at least in part on forward and/or backward citations of the third patent. 
     
     
         11 . The method of  claim 1 , wherein the calculating includes utilizing eigenvector network centrality where the first, second, and third patents are represented as nodes and the forward and backward citations are represented as connections between the nodes. 
     
     
         12 . The method of  claim 1 , wherein the second and third patents are patents that were filed or issued within a predetermined period defined at least in part by the first patent. 
     
     
         13 . The method of  claim 1 , wherein the calculating includes solving the following for π:
   π= P   T π where  P =diag( d ) −1   M  and  d=Me,  
 
 
       where e represents a unitary vector, d represents a vector defined by scaling factors, P represents a matrix, P T  represents a transpose of P, π represents an eigenvector, and M represents a matrix including the first, second, and third patents and corresponding citations. 
     
     
         14 . The method of  claim 1 , wherein the weighting includes weighting the forward citation based at least in part on a similarity between the first patent and second patent, the similarity corresponding to a technology classification, field of search classification, or other classification. 
     
     
         15 . The method of  claim 1 , wherein the weighting includes weighting the backward citation based at least in part on a similarity between the first patent and third patent, the similarity corresponding to a technology classification, field of search classification, or other classification. 
     
     
         16 . One or more computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform acts comprising:
 obtaining a plurality of patents, each of the plurality of patents having a forward citation and a backward citation;   weighting each of the forward and backward citations of h plurality of patents; and   calculating a value for each of the plurality of patents based at leas part on the weighted forward citations and the weighted backward citations.   
     
     
         17 . The one or more computer-readable media of  claim 16 , wherein the calculating includes simultaneously calculating the values of the plurality of patents. 
     
     
         18 . The one or more computer-readable media of  claim 16 , wherein the calculating includes:
 representing the forward and backward citations in a matrix;   sorting the matrix;   augmenting the sorted matrix by adding a row and a column to the matrix;   normalizing rows within the augmented matrix; and   solving the normalized matrix.   
     
     
         19 . The one or more computer-readable media of  claim 18 , wherein the sorting includes classifying the plurality of patents and corresponding citations, and reorganizing the matrix based at least in part on the classification. 
     
     
         20 . The one or more computer-readable media of  claim 18 , wherein the augmenting includes weighting an element within the added column or added row. 
     
     
         21 . The one or more computer-readable media of  claim 18 , wherein the normalizing includes utilizing matrix algebra. 
     
     
         22 . The one or more computer-readable media of  claim 18 , wherein the solving includes utilizing at least one of a power method and a linear-algebra method. 
     
     
         23 . The one or more computer-readable media of  claim 16 , wherein the calculating includes utilizing eigenvector network centrality where the plurality of patents are represented as nodes and the forward and backward citations are represented as connections between the nodes. 
     
     
         24 . The one or more computer-readable media of  claim 16 , wherein the calculating includes solving the following for
   π= P   T π where  P =diag( d ) −1   M  and  d=Me,  
   where e represents a unitary vector, d represents a vector defined by scaling factors, P represents a matrix, P T  represents a transpose of P, π represents an eigenvector, and M represents a matrix including the plurality of patents and corresponding citations.   
     
     
         25 . A system, comprising:
 one or more processors; and   memory, communicatively coupled to the one or more processors, storing a patent valuation module configured to:
 weight a forward citation and a backward citation, the forward citation being a citation in a second patent to a first patent, the backward citation being a citation in the first patent to a third patent, and 
 calculate a value of the first patent based at least in part on the weighted forward citation and weighted backward citation. 
   
     
     
         26 . The system of  claim 25 , wherein the first patent includes at least a plurality of forward or backward citations, and
 the patent valuation module is further configured to:
 weight each of the plurality of forward or backward citations, and 
 calculate the value of the first patent based at least in part on each of the plurality of weighted forward or backward citations. 
   
     
     
         27 . The system of  claim 25 , wherein the patent valuation module is further configured to:
 represent the forward and backward citations in a matrix;   sort the matrix;   augment the sorted matrix by adding a row and a column to the matrix;   normalize rows within the augmented matrix; and   solve the normalized matrix.   
     
     
         28 . The system of  claim 27 , wherein the patent valuation module is configured to sort by classifying the first patent and corresponding citations, and reorganizing the matrix based at least in part on the classification. 
     
     
         29 . The system of  claim 27 , wherein the patent valuation module is configured to augment by weighting an element within the added column or added row. 
     
     
         30 . The system of  claim 27 , wherein the patent valuation module is configured to normalize utilizing matrix algebra. 
     
     
         31 . The system of  claim 27 , wherein the patent valuation module is configured to solve by utilizing at least one of a power method and a linear-algebra method. 
     
     
         32 . The system of  claim 25 , wherein the patent valuation module is further configured to weight the forward citation based at least in part on a value of the second patent, and weight the backward citation based at least in part on a value of the third patent. 
     
     
         33 . The system of  claim 32 , wherein the value of the second patent is based at least in part on forward and/or backward citations of the second patent, and the value of the third patent is based at least in part on forward and/or backward citations of the third patent. 
     
     
         34 . The system of  claim 25 , wherein the patent valuation module is further configured to utilize eigenvector network centrality to calculate the value of the first patent, the first, second, and third patents being represented as nodes and the forward and backward citations being represented as connections between the nodes. 
     
     
         35 . The system of  claim 25 , wherein the second and third patents are patents that were filed or issued within a predetermined period defined at least in part by the first patent. 
     
     
         36 . The system of  claim 25 , wherein the patent valuation module is configured to calculate the value of the first patent by solving the following for π:
   π= P   T π where  P =diag( d ) −1   M  and  d=Me,  
 
 where e represents a unitary vector, d represents a vector defined by scaling factors, P represents a matrix, P T  represents a transpose of P, π represents an eigenvector, and M represents a matrix including the first, second, and third patents and corresponding citations.